ModelPaddleOCR-VL-1.6
PaddleOCR-VL
A multimodal OCR and document parsing model developed by Baidu's PaddlePaddle team, supporting vision-language tasks, with evaluation results on OmniDocBench.
Timeline (last 90 days)
Oct 12
On OmniDocBench v1.6, TeleOCR outperforms Youtu-Parsing-Omni on text edit distance and table TEDS; OvisOCR2 and PaddleOCR-VL surpass Youtu on formulas with fewer than 1B parameters.
Unverified50%
Aug 28
该方案将DeepSeek-OCR-2、GLM-OCR、dots.mocr、PaddleOCR-VL、PP-OCRv6这五款开源OCR模型集中在同一个端点之后
Unverified50%